{"id":"https://openalex.org/W7125904633","doi":"https://doi.org/10.1109/smc58881.2025.11343333","title":"A Unified Two-Stage Framework for Human-Aligned Information Extraction Using Large Language Models","display_name":"A Unified Two-Stage Framework for Human-Aligned Information Extraction Using Large Language Models","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125904633","doi":"https://doi.org/10.1109/smc58881.2025.11343333"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11343333","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343333","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046750593","display_name":"Zhiheng Ning","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiheng Ning","raw_affiliation_strings":["Tongji University,School of Computer Science and Technology,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University,School of Computer Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wenlin Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenlin Jiang","raw_affiliation_strings":["Tongji University,School of Computer Science and Technology,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University,School of Computer Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124115698","display_name":"Han Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Lu","raw_affiliation_strings":["Tongji University,School of Computer Science and Technology,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University,School of Computer Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050985632","display_name":"Meng Luo","orcid":"https://orcid.org/0000-0002-0703-2633"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojun Li","raw_affiliation_strings":["Ministry of Education, Tongji University,Engineering Research Center of Civil-Informatics,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ministry of Education, Tongji University,Engineering Research Center of Civil-Informatics,Shanghai,China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4853","last_page":"4860"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6700000166893005,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6700000166893005,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.03220000118017197,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.032099999487400055,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.758400022983551},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.7021999955177307},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5268999934196472},{"id":"https://openalex.org/keywords/schema-matching","display_name":"Schema matching","score":0.4984000027179718},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.49309998750686646},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.48089998960494995},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.36719998717308044},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"Unstructured data","score":0.34369999170303345}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7742999792098999},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.758400022983551},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.7021999955177307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6018999814987183},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5268999934196472},{"id":"https://openalex.org/C2777327318","wikidata":"https://www.wikidata.org/wiki/Q1408390","display_name":"Schema matching","level":3,"score":0.4984000027179718},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.49309998750686646},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.48089998960494995},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46070000529289246},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44209998846054077},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.36719998717308044},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3589000105857849},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.34369999170303345},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3197999894618988},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.31119999289512634},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.30880001187324524},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2937000095844269},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.2644999921321869},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C77660490","wikidata":"https://www.wikidata.org/wiki/Q244916","display_name":"Intermediate language","level":3,"score":0.26019999384880066}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11343333","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343333","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5865710973739624,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2099779943","https://openalex.org/W2963971244","https://openalex.org/W3035229828","https://openalex.org/W3106098584","https://openalex.org/W3167136668","https://openalex.org/W3173156538","https://openalex.org/W4221166835","https://openalex.org/W4281488715","https://openalex.org/W4283704460","https://openalex.org/W4385570525","https://openalex.org/W4385571184","https://openalex.org/W4385572217","https://openalex.org/W4385767863","https://openalex.org/W4389523710","https://openalex.org/W4391681328","https://openalex.org/W4401044087","https://openalex.org/W4402671778","https://openalex.org/W4403942906","https://openalex.org/W4404783059","https://openalex.org/W4404783098","https://openalex.org/W4411120260"],"related_works":[],"abstract_inverted_index":{"The":[0,143],"information":[1],"extraction":[2],"(IE)":[3],"task,":[4],"aims":[5],"to":[6,15,38,57,89],"transform":[7],"unstructured":[8],"text":[9],"into":[10],"structured":[11,48,149],"knowledge.":[12],"How-ever,":[13],"due":[14],"challenges":[16],"in":[17,28,41,110,126,136,155],"human":[18,94],"needs":[19],"alignment,":[20],"large":[21],"language":[22],"models":[23],"(LLMs)":[24],"often":[25],"struggle":[26],"with":[27,93],"IE":[29,42,104,128,163],"tasks.":[30,43],"This":[31],"paper":[32],"proposes":[33],"a":[34,47,67,119],"unified":[35],"two-stage":[36,68],"framework":[37],"enhance":[39,61],"LLMs":[40,160],"First,":[44],"we":[45,65],"introduce":[46],"schema":[49,75,150],"representation":[50,151],"using":[51,83],"JSON-LD":[52],"(JSON":[53],"for":[54,74,100,130],"Linked":[55],"Data)":[56],"eliminate":[58],"ambiguity":[59],"and":[60,102,113,124,133,152,161],"model":[62],"robustness.":[63],"Second,":[64],"design":[66],"learning":[69],"method:":[70],"supervised":[71,114],"fine-tuning":[72],"(SFT)":[73],"understanding,":[76],"followed":[77],"by":[78],"direct":[79],"preference":[80,153],"optimization":[81],"(DPO),":[82],"an":[84],"automatic":[85],"negative":[86],"sampling":[87],"strategy":[88],"align":[90],"the":[91,127,146,157],"output":[92],"preferences.":[95],"Experiments":[96],"on":[97],"19":[98],"datasets":[99],"general":[101],"domain-specific":[103],"tasks":[105],"show":[106],"state-of-the-art":[107],"(SoTA)":[108],"performance":[109],"both":[111],"zero-shot":[112],"settings.":[115],"Our":[116],"method":[117],"achieves":[118],"relative":[120],"improvement":[121],"of":[122,148],"6.7%":[123],"19.6%":[125],"ability":[129],"unseen":[131],"schemas,":[132],"maintains":[134],"robustness":[135],"fine-grained":[137],"entity":[138],"recognition,":[139],"outperforming":[140],"existing":[141],"baselines.":[142],"results":[144],"highlight":[145],"effectiveness":[147],"alignment":[154],"bridging":[156],"gap":[158],"between":[159],"complex":[162],"requirements.":[164]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-01-29T00:00:00"}